LLM API pricing

Compare per-token prices across LLM API providers.

3,516
Chat models
18
Providers
Free
Lowest input / 1M tokens
10.5M
Largest context

LLM market heatmap

3,582 models grouped by vendor — click a vendor, then a family to filter the catalog

DEAL% · listings-weighted · signed (− red / + green) · n=24/29

Models

1,510 models
ModelProvidersInput from / 1MOutput from / 1MContextCapabilities
Qwen Qwen3 32b Fp81$0.10/1M tokens$0.45/1M tokens40,960 Reasoning
OpenAI: GPT-5.4 Nano (batch)1$0.10/1M tokens$0.63/1M tokens400,000Vision FC Reasoning
OpenAI: GPT-5.6 Luna Pro (batch)1$0.10/1M tokens$0.60/1M tokens1,050,000Vision FC Reasoning
OpenAI: GPT-5.6 Luna (batch)1$0.10/1M tokens$0.60/1M tokens1,050,000Vision FC Reasoning
Google Gemini 2 5 Flash Lite1$0.10/1M tokens$0.40/1M tokens1,048,576Vision FC Reasoning
Qwen Qwen3 5 9b1$0.10/1M tokens$0.15/1M tokens262,144Vision FC Reasoning
Qwen Qwen3 6 35b A3b1$0.10/1M tokens$0.90/1M tokens262,144Vision FC Reasoning
Xiaomi Mimo V2 Flash1$0.10/1M tokens$0.30/1M tokens262,144 FC Reasoning
Ps Deepseek V4 Flash1$0.10/1M tokens$0.20/1M tokens163,840 FC Reasoning
Qwen: Qwen3.5-9B1$0.10/1M tokens$0.15/1M tokens262,144Vision FC Reasoning
Qwen: Qwen3.6 35B A3B1$0.10/1M tokens$0.90/1M tokens262,144Vision FC Reasoning
Reka Flash 31$0.10/1M tokens$0.20/1M tokens65,536 Reasoning
StepFun: Step 3.5 Flash1$0.10/1M tokens$0.30/1M tokens262,144 FC Reasoning
Qwen Qwen3 235B A22B Thinking 25071$0.10/1M tokens$0.10/1M tokens262,144 Reasoning
Google Gemma 4 31B It1$0.10/1M tokens$0.34/1M tokens262,144Vision Reasoning
Ibm Granite Granite 4 2 8b1$0.10/1M tokens$0.15/1M tokens Reasoning
Nvidia NVIDIA Nemotron 3 5 Lightning 30B A3B1$0.10/1M tokens$0.25/1M tokens262,144 Reasoning
DeepSeek: DeepSeek V4 Flash 0731 (batch)1$0.11/1M tokens$0.33/1M tokens1,048,576 FC Reasoning
DeepSeek: DeepSeek V4 Flash Vision Exp (batch)1$0.11/1M tokens$0.33/1M tokens1,048,576Vision FC Reasoning
Xiaomimimo Mimo V2 Flash1$0.11/1M tokens$0.33/1M tokens262,144 FC Reasoning
Qwen Qwen3 14b1$0.12/1M tokens$0.24/1M tokens131,072 FC Reasoning
Qwen Qwen3 30b A3b1$0.12/1M tokens$0.50/1M tokens131,072 FC Reasoning
Qwen Qwen3 8b1$0.12/1M tokens$0.46/1M tokens131,072 FC Reasoning
Qwen: Qwen3 30B A3B1$0.12/1M tokens$0.50/1M tokens131,072 FC Reasoning
Qwen: Qwen3 8B1$0.12/1M tokens$0.46/1M tokens131,072 FC Reasoning
Phi 4 Reasoning1$0.13/1M tokens$0.50/1M tokens32,768 FC Reasoning
Google Gemma 4 26b A4b1$0.13/1M tokens$0.40/1M tokens256,000Vision FC Reasoning
Google Gemma 4 31B It1$0.13/1M tokens$0.38/1M tokens262,144Vision FC Reasoning
Google: Gemini 3.1 Flash Lite (batch)1$0.13/1M tokens$0.75/1M tokens1,048,576Vision FC Reasoning
NousResearch Hermes 4 70B1$0.13/1M tokens$0.40/1M tokens131,072 FC Reasoning
Google Gemma 4 26b A4b It1$0.13/1M tokens$0.40/1M tokens262,144Vision FC Reasoning
Zai Org Glm 4 5 Air1$0.13/1M tokens$0.85/1M tokens131,072 FC Reasoning
OpenAI: GPT-5 Mini (batch)1$0.13/1M tokens$1.00/1M tokens400,000Vision FC Reasoning
Z Ai Glm 4 5 Air1$0.13/1M tokens$0.85/1M tokens131,072 FC Reasoning
Ps Glm 4 5 Air1$0.13/1M tokens$0.45/1M tokens128,000 FC Reasoning
Tencent: Hy31$0.13/1M tokens$0.53/1M tokens262,144 FC Reasoning
Deepseek Ai DeepSeek V4 Flash 07311$0.13/1M tokens$0.28/1M tokens262,144 Reasoning
Z.ai: GLM 4.5 Air1$0.13/1M tokens$0.85/1M tokens131,072 FC Reasoning
Google Gemma 4 31b1$0.14/1M tokens$0.40/1M tokens256,000Vision FC Reasoning
Databricks Deepseek V4 Flash 07311$0.14/1M tokens$0.28/1M tokens1,000,000 FC Reasoning
Qwen Qwen3 5 35B A3B1$0.14/1M tokens$1.00/1M tokens262,144Vision FC Reasoning
Tencent Hy31$0.14/1M tokens$0.58/1M tokens262,144 FC Reasoning
DeepSeek V4 Flash1$0.14/1M tokens$0.28/1M tokens1,048,576 FC Reasoning
Accounts Fireworks Models Deepseek V4 Flash1$0.14/1M tokens$0.28/1M tokens1,048,576 FC Reasoning
Deepseek V4 Flash1$0.14/1M tokens$0.28/1M tokens1,048,576 FC Reasoning
Deepseek Ai DeepSeek V4 Flash1$0.14/1M tokens$0.28/1M tokens1,048,576 FC Reasoning
Deepseek Ai DeepSeek V4 Flash 07311$0.14/1M tokens$0.28/1M tokens1,024,000 FC Reasoning
Baidu Ernie 4 5 Vl 28b A3b1$0.14/1M tokens$0.56/1M tokens30,000Vision FC Reasoning
Deepseek Deepseek V4 Flash1$0.14/1M tokens$0.28/1M tokens1,048,576 FC Reasoning
Google Gemma 4 31b It1$0.14/1M tokens$0.40/1M tokens262,144Vision FC Reasoning
Tencent Hy31$0.14/1M tokens$0.58/1M tokens262,144 FC Reasoning
Xiaomi Mimo V2 51$0.14/1M tokens$0.28/1M tokens1,048,576Vision FC Reasoning
Ps Qwen3 6 35b A3b1$0.14/1M tokens$0.45/1M tokens131,072 FC Reasoning
Deepseek V4 Flash1$0.14/1M tokens$0.28/1M tokens1,000,000 FC Reasoning
Tencent: Hunyuan A13B Instruct1$0.14/1M tokens$0.57/1M tokens131,072 Reasoning
Deepseek Ai DeepSeek V4 Flash1$0.14/1M tokens$0.28/1M tokens32,768 FC Reasoning
Google Gemma 4 31B It1$0.14/1M tokens$0.56/1M tokens32,768 FC Reasoning
Deepseek Ai DeepSeek V4 Flash1$0.14/1M tokens$0.28/1M tokens1,048,576 Reasoning
Xiaomi: MiMo-V2.51$0.14/1M tokens$0.28/1M tokens1,050,000Vision FC Reasoning
Openai Gpt Oss 120b1$0.15/1M tokens$0.60/1M tokens131,072 FC Reasoning
Openai Gpt Oss Safeguard 120b1$0.15/1M tokens$0.60/1M tokens131,072 FC Reasoning
Qwen3 Next 80b A3b Thinking1$0.15/1M tokens$1.20/1M tokens262,144 FC Reasoning
Databricks Glm 5 3 Flash1$0.15/1M tokens$0.50/1M tokens1,048,576Vision FC Reasoning
Openai Gpt Oss 120b Turbo1$0.15/1M tokens$0.60/1M tokens131,072 FC Reasoning
DeepSeek: DeepSeek V4.1 Flash1$0.15/1M tokens$0.60/1M tokens1,048,576Vision FC Reasoning
文心 ERNIE X1 Turbo1$0.15/1M tokens$0.59/1M tokens128,000 Reasoning
Accounts Fireworks Models Gpt Oss 120b1$0.15/1M tokens$0.60/1M tokens131,072 FC Reasoning
Gpt Oss 120b1$0.15/1M tokens$0.60/1M tokens131,072 FC Reasoning
Zai Org GLM 5 3 Flash1$0.15/1M tokens$0.50/1M tokens1,048,576Vision FC Reasoning
Google: Gemini 2.5 Flash (batch)1$0.15/1M tokens$1.25/1M tokens1,048,576Vision FC Reasoning
Google: Gemini 3.5 Flash Lite (batch)1$0.15/1M tokens$1.25/1M tokens1,048,576Vision FC Reasoning
Openai Gpt Oss 120b1$0.15/1M tokens$0.60/1M tokens131,072 FC Reasoning
混元 T11$0.15/1M tokens$0.59/1M tokens64,000 Reasoning
Gemma 4 31b It Thinking1$0.15/1M tokens$0.40/1M tokens262,144Vision FC Reasoning
Qwen3 6 27b Thinking1$0.15/1M tokens$0.50/1M tokens262,144Vision FC Reasoning
Qwen3 6 35b A3b Thinking1$0.15/1M tokens$0.50/1M tokens262,144Vision FC Reasoning
Magistral Small Latest1$0.15/1M tokens$0.60/1M tokens262,144Vision FC Reasoning
Mistral Small 26031$0.15/1M tokens$0.60/1M tokens262,144Vision FC Reasoning
Mistral Small Latest1$0.15/1M tokens$0.60/1M tokens262,144Vision FC Reasoning
Mistral Vibe Cli Fast1$0.15/1M tokens$0.60/1M tokens262,144Vision FC Reasoning
Mistral: Mistral Small 41$0.15/1M tokens$0.60/1M tokens262,144Vision FC Reasoning
Qwen QwQ 32B1$0.15/1M tokens$0.45/1M tokens32,768 FC Reasoning
Qwen Qwen3 Next 80B A3B Thinking1$0.15/1M tokens$1.20/1M tokens128,000 FC Reasoning
Openai Gpt Oss 120b1$0.15/1M tokens$0.60/1M tokens131,072 FC Reasoning
Zai Org GLM 5 3 Flash1$0.15/1M tokens$0.50/1M tokens1,024,000 FC Reasoning
Deepseek Deepseek R1 Distill Qwen 14b1$0.15/1M tokens$0.15/1M tokens32,768 Reasoning
Qwen Qwen3 Next 80b A3b Instruct1$0.15/1M tokens$1.50/1M tokens131,072 FC Reasoning
Qwen Qwen3 Next 80b A3b Thinking1$0.15/1M tokens$1.50/1M tokens131,072 FC Reasoning
Nvidia Nemotron Super 3 120b1$0.15/1M tokens$0.65/1M tokens256,000 FC Reasoning
Openai Gpt Oss 120b 1 01$0.15/1M tokens$0.60/1M tokens128,000 FC Reasoning
OpenAI: gpt-oss-120b (batch)1$0.15/1M tokens$0.60/1M tokens131,072 FC Reasoning
Mistralai Mistral Small 26031$0.15/1M tokens$0.60/1M tokens262,144Vision FC Reasoning
Qwen Qwen3 Next 80b A3b Thinking1$0.15/1M tokens$1.20/1M tokens262,144 FC Reasoning
Qwen Qwen3 8 Flash1$0.15/1M tokens$0.47/1M tokens1,000,000Vision FC Reasoning
Perceptron: Perceptron Mk11$0.15/1M tokens$1.50/1M tokens32,768Vision Reasoning
Qwen Qwen3 32b V1 01$0.15/1M tokens$0.60/1M tokens131,072 FC Reasoning
Qwen Qwen3 Coder 30b A3b V1 01$0.15/1M tokens$0.60/1M tokens262,144 FC Reasoning
Qwen: Qwen3 Next 80B A3B Thinking1$0.15/1M tokens$1.20/1M tokens262,144 FC Reasoning
Qwen: Qwen3.8 Flash1$0.15/1M tokens$0.47/1M tokens1,000,000Vision FC Reasoning
Qwen3 Next 80b A3b Thinking1$0.15/1M tokens$1.20/1M tokens262,144 FC Reasoning